© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3038
    Prev
    Next
    INDEX
    Explanations

    numbers followed by certain characters

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on single‐quote characters (apostrophes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    傅
    -1.02
    thinkable
    -0.94
    ,:,
    -0.94
    ccedil
    -0.94
    ,:),
    -0.90
    评估
    -0.90
    })()
    -0.89
    -0.89
    jiny
    -0.89
    </th>
    -0.89
    POSITIVE LOGITS
     forums
    1.06
    Instru
    1.03
    ihnachten
    1.03
    inerario
    1.02
     forum
    1.02
     ursprünglichen
    0.98
    ihnachts
    0.91
    rikt
    0.91
     aspiring
    0.90
     térmica
    0.90
    Activations Density 0.019%

    No Known Activations